GFS_GP_R {RKEEL}

GFS_GP_R KEEL Regression Algorithm

Description

GFS_GP_R Regression Algorithm from KEEL.

Usage

GFS_GP_R(train, test, numLabels, numRules, popSize, numisland,
   steady, numIter, tourSize, mutProb, aplMut, probMigra,
   probOptimLocal, numOptimLocal, idOptimLocal, nichinggap,
   maxindniche, probintraniche, probcrossga, probmutaga,
   lenchaingap, maxtreeheight, seed)

Arguments

train

Train dataset as a data.frame object

test

Test dataset as a data.frame object

numLabels

numLabels. Default value = 3

numRules

numRules. Default value = 8

popSize

popSize. Default value = 30

numisland

numisland. Default value = 2

steady

steady. Default value = 1

numIter

numIter. Default value = 100

tourSize

tourSize. Default value = 4

mutProb

mutProb. Default value = 0.01

aplMut

aplMut. Default value = 0.1

probMigra

probMigra. Default value = 0.001

probOptimLocal

probOptimLocal. Default value = 0.00

numOptimLocal

numOptimLocal. Default value = 0

idOptimLocal

idOptimLocal. Default value = 0

nichinggap

nichinggap. Default value = 0

maxindniche

maxindniche. Default value = 8

probintraniche

probintraniche. Default value = 0.75

probcrossga

probcrossga. Default value = 0.5

probmutaga

probmutaga. Default value = 0.5

lenchaingap

lenchaingap. Default value = 10

maxtreeheight

maxtreeheight. Default value = 8

seed

Seed for random numbers. If it is not assigned a value, the seed will be a random number

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::GFS_GP_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions